CN112009397B - Automatic driving drive test data analysis method and device - Google Patents
Automatic driving drive test data analysis method and device Download PDFInfo
- Publication number
- CN112009397B CN112009397B CN202010763661.5A CN202010763661A CN112009397B CN 112009397 B CN112009397 B CN 112009397B CN 202010763661 A CN202010763661 A CN 202010763661A CN 112009397 B CN112009397 B CN 112009397B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- driver
- speed
- braking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
- B60R16/0231—Circuits relating to the driving or the functioning of the vehicle
- B60R16/0232—Circuits relating to the driving or the functioning of the vehicle for measuring vehicle parameters and indicating critical, abnormal or dangerous conditions
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention provides an automatic driving drive test data analysis method and device, wherein the method comprises the following steps: acquiring CAN data corresponding to the moment when a driver actively takes over in automatic driving, and extracting key data of the CAN data in an automatic taking over scene to obtain a CAN data set; drawing a scatter diagram according to the CAN data set, and performing regression curve fitting based on the scatter diagram to obtain a threshold model which is actively taken over by a driver; and generating an AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver. By the scheme, the problem of high cost of the existing threshold test is solved, the threshold extraction test cost can be reduced, and the vehicle driving safety is guaranteed.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to an automatic driving drive test data analysis method and device.
Background
With the maturity of automatic driving technology, manual driving by a driver can be separated in many scenes, and active takeover is still needed in some scenes with potential danger, and excessive active takeover not only influences the driving experience, but also can bring potential danger.
The current automatic driving system usually adopts a mode of presetting a danger threshold value to carry out active takeover judgment, and reminds a driver to take over when the driving parameters of the vehicle reach the danger threshold value, or carries out automatic braking adjustment. However, the setting of the danger threshold requires a large amount of test data, and further requires adjustment and correction according to different surrounding scene environments, which greatly increases the test cost of the driving system.
Disclosure of Invention
In view of this, embodiments of the present invention provide an automatic driving test data analysis method and apparatus, so as to solve the problem that the cost of taking over a threshold test by an existing driving system is high.
In a first aspect of an embodiment of the present invention, there is provided an automatic driving test data analysis method, including:
acquiring CAN data corresponding to the moment when a driver actively takes over in automatic driving, and extracting key data of the CAN data in an automatic taking over scene to obtain a CAN data set;
drawing a scatter diagram according to the CAN data set, and performing regression curve fitting based on the scatter diagram to obtain a threshold model which is actively taken over by a driver;
and generating an AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver.
In a second aspect of the embodiments of the present invention, there is provided an automatic drive test data analysis device including:
the extraction module is used for acquiring CAN data corresponding to the moment when the driver actively takes over the automatic driving, and extracting key data of the CAN data in the scene of automatic taking over to obtain a CAN data set;
the fitting module is used for drawing a scatter diagram according to the CAN data set and performing regression curve fitting on the basis of the scatter diagram to obtain a threshold model which is actively taken over by a driver;
and the generating module is used for generating the AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver.
In a third aspect of the embodiments of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method according to the first aspect of the embodiments of the present invention.
In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method provided in the first aspect of the embodiments of the present invention.
In the embodiment of the invention, the CAN data corresponding to the moment that a driver actively takes over the automatic driving is obtained, and the key data extraction is carried out on the CAN data in the scene of automatic taking over to obtain a CAN data set; drawing a scatter diagram according to the CAN data set, and performing regression curve fitting based on the scatter diagram to obtain a threshold model which is actively taken over by a driver; and generating an AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver. The method has the advantages that the threshold model when the vehicle actively takes over can be obtained, the vehicle braking rule corresponding to the scene can be set, the threshold model can be extracted based on analysis of a large amount of drive test data, existing test data can be effectively utilized, and the taking over threshold test cost can be effectively reduced, so that the problem that the existing automatic driving system is high in taking over threshold test cost is solved, meanwhile, the corresponding braking rule can be preset in the driving system, the vehicle driving safety is guaranteed, active taking over is avoided, and the driving experience is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of an analysis method of automatic driving test data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an automatic drive test data analysis apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons skilled in the art without any inventive work shall fall within the protection scope of the present invention, and the principle and features of the present invention shall be described below with reference to the accompanying drawings.
The terms "comprises" and "comprising," when used in this specification and claims, and in the accompanying drawings and figures, are intended to cover non-exclusive inclusions, such that a process, method or system, or apparatus that comprises a list of steps or elements is not limited to the listed steps or elements.
In the general real vehicle drive test process, the performance of the automatic driving function in a complex scene can be effectively verified. By recording the scene of function failure, data playback test can be carried out at the later stage. The data volume of real vehicle road test is huge, the data is not fully mined and utilized by the existing data analysis method, and the data value of the data is found.
Referring to fig. 1, fig. 1 is a schematic flow chart of an automatic driving test data analysis method according to an embodiment of the present invention, including:
s101, acquiring CAN data corresponding to the moment when a driver takes over the automatic driving actively, and extracting key data of the CAN data in the scene of taking over automatically to obtain a CAN data set;
the active take-over means that a driver actively operates and controls the running of the vehicle, such as stepping on a brake pedal or rotating a steering wheel, and the like, and CAN data of the vehicle at the moment are collected. CAN data at the moment that a vehicle actively takes over under a plurality of scenes are usually collected.
The key data are some vehicle control parameters in the CAN data, such as vehicle running speed, and measured data, such as distance to a target vehicle or an obstacle and target vehicle running speed.
The CAN data set comprises the speed of the vehicle, the relative speed of the vehicle and the target vehicle, the longitudinal and transverse distances between the vehicle and the target vehicle, the collision time and the headway. The collision time and the headway are calculated according to the speed of the vehicle, the relative speed and the relative distance between the vehicle and the target vehicle.
The conventional danger definition takes TTC (time to collision) as a single judgment index, and when the speeds of two vehicles are close and the distance between the two vehicles is small, the TTC (time to collision) is larger but still belongs to a dangerous scene, so THW (headway) is introduced to make up for the missed judgment of the potential dangerous scene.
S102, drawing a scatter diagram according to the CAN data set, and performing regression curve fitting based on the scatter diagram to obtain a threshold model which is actively taken over by a driver;
and drawing scatter diagrams of data distribution in CAN data concentration under different automatic takeover scenes by taking the longitudinal distance between the self vehicle and the target vehicle as a horizontal coordinate and the collision time and the vehicle head time interval as vertical coordinates.
And performing regression curve fitting based on the scatter diagram, obtaining the speed of the vehicle and the critical value of the relative speed of the vehicle and other vehicles in different vehicle speed sections, and forming a threshold value model which is actively taken over by a driver, wherein the critical value is the safe distance between the vehicle and other vehicles.
S103, according to the threshold model actively taken over by the driver, generating the AEB braking rule of the vehicle under different driving conditions.
The braking rule of the vehicle AEB (automated ignition braking), namely the active and safe braking rule of the vehicle, is used for controlling the vehicle to ensure safe driving. Based on the threshold model, an AEB algorithm braking rule can be designed.
Specifically, according to the speed of the vehicle, the speed of the target vehicle, the relative distance between the vehicle and the target vehicle, the road braking standard, the weather and the threshold model, corresponding vehicle braking schemes under different speeds of the vehicle, relative distances of the vehicle, braking standards and weather are generated, so that the following distance and the braking distance of the automatic driving vehicle can meet preset requirements. I.e. braking scenarios when the autonomous vehicle needs to take over actively at different vehicle speeds, different relative speeds to the target vehicle, different relative distances to the target vehicle, different road braking standards, and different weather.
According to a threshold model established by a natural driving data set, the performance condition of the AEB algorithm in a test scene can be judged, if the braking point exceeds a threshold value and upper and lower maximum deviation values, the untimely braking control of the algorithm in the scene can be judged, and corresponding safety evaluation is given according to the deviation of the braking point.
In this embodiment, through taking over scene data extraction analysis to the initiative in the real vehicle drive test, obtain the driving threshold value model that corresponds under the scene is taken over to multiple, and then can carry out the braking rule and set for, when the guarantee vehicle safety of traveling, can effectively reduce initiative and take over, promote driving experience, simultaneously, reduce and take over the threshold value and set for and test the cost that brings at the tradition.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 2 is a schematic structural diagram of an automatic driving test data analysis device according to an embodiment of the present invention, where the device includes:
the extraction module 210 is configured to acquire CAN data corresponding to a moment when a driver actively takes over in automatic driving, and extract key data of the CAN data in an automatic taking over scene to obtain a CAN data set;
the CAN data set comprises the speed of the vehicle, the relative speed of the vehicle and the target vehicle, the longitudinal and transverse distances between the vehicle and the target vehicle, collision time and headway.
The fitting module 220 is used for drawing a scatter diagram according to the CAN data set and performing regression curve fitting based on the scatter diagram to obtain a threshold model which is actively taken over by the driver;
specifically, the drawing a scatter diagram according to the CAN data set includes:
and drawing scatter diagrams of data distribution in CAN data concentration under different automatic takeover scenes by taking the longitudinal distance between the self vehicle and the target vehicle as a horizontal coordinate and the collision time and the vehicle head time interval as vertical coordinates.
Further, performing regression curve fitting based on the scatter diagram, obtaining the speed of the vehicle and the critical value of the relative speed of the vehicle and other vehicles in different vehicle speed sections, and forming a threshold value model which is actively taken over by a driver, wherein the critical value is the safe distance between the vehicle and other vehicles.
And the generating module 230 is configured to generate an AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver.
Specifically, the generating module 230 includes:
and the generating unit is used for generating corresponding vehicle braking schemes under different vehicle speeds, vehicle relative speeds, relative distances, braking standards and weather according to the vehicle speed, the target vehicle speed, the relative distance between the vehicle and the target vehicle, the road braking standard, the weather and the threshold model so as to ensure that the following distance and the braking distance of the automatic driving vehicle meet preset requirements.
It will be appreciated by those of ordinary skill in the art that in one embodiment, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing steps S101 to S103 when executing the computer program to analyze the road test data to generate the braking rule.
Those skilled in the art will also understand that all or part of the steps in the method for implementing the above embodiments may be implemented by a program to instruct associated hardware, where the program may be stored in a computer-readable storage medium, and when the program is executed, the program includes steps S101 to S103, where the storage medium includes, for example: ROM/RAM, magnetic disk, optical disk, etc.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. An automated driving test data analysis method, comprising:
acquiring CAN data corresponding to the moment when a driver actively takes over in automatic driving, and extracting key data of the CAN data in an automatic taking over scene to obtain a CAN data set;
drawing a scatter diagram according to the CAN data set, and performing regression curve fitting based on the scatter diagram to obtain a threshold model which is actively taken over by a driver;
the method comprises the following steps of drawing scatter diagrams of CAN data centralized data distribution under different automatic takeover scenes by taking the longitudinal distance between a self vehicle and a target vehicle as a horizontal coordinate and the collision time and the vehicle head time interval as vertical coordinates;
performing regression curve fitting based on the scatter diagram, obtaining the speed of the vehicle and the critical value of the relative speed of the vehicle and other vehicles in different vehicle speed sections, and forming a threshold value model which is actively taken over by a driver, wherein the critical value is the safe distance between the vehicle and other vehicles;
and generating an AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver.
2. The method of claim 1 wherein the CAN data set comprises a speed of the host vehicle, a relative speed of the host vehicle to the target vehicle, longitudinal and lateral distances of the host vehicle to the target vehicle, a time to collision, and a headway.
3. The method of claim 1, wherein generating vehicle AEB braking rules for different driving conditions according to the driver-proactive-takeover-threshold model comprises:
and generating corresponding vehicle braking schemes under different vehicle speeds, vehicle relative distances, braking standards and weather according to the vehicle speed, the target vehicle speed, the relative distance between the vehicle and the target vehicle, the road braking standard, the weather and a threshold model so as to ensure that the following distance and the braking distance of the automatic driving vehicle meet preset requirements.
4. A road tag generating device, comprising:
the extraction module is used for acquiring CAN data corresponding to the moment when the driver actively takes over the automatic driving, and extracting key data of the CAN data in the scene of automatic taking over to obtain a CAN data set;
the fitting module is used for drawing a scatter diagram according to the CAN data set and performing regression curve fitting on the basis of the scatter diagram to obtain a threshold model which is actively taken over by a driver;
the method comprises the following steps of drawing scatter diagrams of CAN data centralized data distribution under different automatic takeover scenes by taking the longitudinal distance between a self vehicle and a target vehicle as a horizontal coordinate and the collision time and the vehicle head time interval as vertical coordinates;
performing regression curve fitting based on the scatter diagram, obtaining the speed of the vehicle and the critical value of the relative speed of the vehicle and other vehicles in different vehicle speed sections, and forming a threshold value model which is actively taken over by a driver, wherein the critical value is the safe distance between the vehicle and other vehicles;
and the generating module is used for generating the AEB braking rule of the vehicle under different driving conditions according to the threshold model actively taken over by the driver.
5. The apparatus of claim 4 wherein the CAN data set comprises a speed of the host vehicle, a relative speed of the host vehicle to the target vehicle, longitudinal and lateral distances of the host vehicle to the target vehicle, a time to collision, and a headway.
6. An electronic device comprising a processor, a memory, and a computer program stored in and run on the memory, wherein the steps of the automated driving test data analysis method according to any one of claims 1 to 3 are implemented when the computer program is executed by the processor.
7. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the automated driving test data analysis method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010763661.5A CN112009397B (en) | 2020-07-31 | 2020-07-31 | Automatic driving drive test data analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010763661.5A CN112009397B (en) | 2020-07-31 | 2020-07-31 | Automatic driving drive test data analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112009397A CN112009397A (en) | 2020-12-01 |
| CN112009397B true CN112009397B (en) | 2022-03-08 |
Family
ID=73499007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010763661.5A Active CN112009397B (en) | 2020-07-31 | 2020-07-31 | Automatic driving drive test data analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112009397B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113022520B (en) * | 2021-05-27 | 2021-08-13 | 天津所托瑞安汽车科技有限公司 | Adaptive braking method, apparatus and storage medium |
| CN113460061B (en) * | 2021-07-08 | 2022-05-31 | 武汉光庭信息技术股份有限公司 | Driving behavior analysis method and system |
| CN114407918B (en) * | 2021-12-30 | 2023-03-14 | 广州文远知行科技有限公司 | Takeover scene analysis method, takeover scene analysis device, takeover scene analysis equipment and storage medium |
| CN114882477A (en) * | 2022-03-04 | 2022-08-09 | 吉林大学 | Method for predicting automatic driving takeover time by using eye movement information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101778741A (en) * | 2007-07-24 | 2010-07-14 | 日产自动车株式会社 | Drive assistance system and method for vehicle and vehicle equipped with the system |
| CN105966396A (en) * | 2016-05-13 | 2016-09-28 | 江苏大学 | Vehicle collision avoidance control method based on driver collision avoidance behavior |
| CN106314428A (en) * | 2016-09-14 | 2017-01-11 | 中国科学院微电子研究所 | Collision avoidance system, collision avoidance method and motor vehicle |
| CN108891350A (en) * | 2018-07-27 | 2018-11-27 | 武汉理工大学 | A kind of rear-end collision prevention early warning system and method based on front truck operator brake habit |
| CN109801511A (en) * | 2017-11-16 | 2019-05-24 | 华为技术有限公司 | A kind of anti-collision warning method and device |
| CN109808706A (en) * | 2019-02-14 | 2019-05-28 | 上海思致汽车工程技术有限公司 | Learning type assistant driving control method, device, system and vehicle |
-
2020
- 2020-07-31 CN CN202010763661.5A patent/CN112009397B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101778741A (en) * | 2007-07-24 | 2010-07-14 | 日产自动车株式会社 | Drive assistance system and method for vehicle and vehicle equipped with the system |
| CN105966396A (en) * | 2016-05-13 | 2016-09-28 | 江苏大学 | Vehicle collision avoidance control method based on driver collision avoidance behavior |
| CN106314428A (en) * | 2016-09-14 | 2017-01-11 | 中国科学院微电子研究所 | Collision avoidance system, collision avoidance method and motor vehicle |
| CN109801511A (en) * | 2017-11-16 | 2019-05-24 | 华为技术有限公司 | A kind of anti-collision warning method and device |
| CN108891350A (en) * | 2018-07-27 | 2018-11-27 | 武汉理工大学 | A kind of rear-end collision prevention early warning system and method based on front truck operator brake habit |
| CN109808706A (en) * | 2019-02-14 | 2019-05-28 | 上海思致汽车工程技术有限公司 | Learning type assistant driving control method, device, system and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112009397A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112009397B (en) | Automatic driving drive test data analysis method and device | |
| CN108773373B (en) | Method and device for operating an autonomous vehicle | |
| EP3460613B1 (en) | Speed planning method and apparatus and calculating apparatus for automatic driving of vehicle | |
| CN111267846B (en) | Game theory-based peripheral vehicle interaction behavior prediction method | |
| US20220048536A1 (en) | Method and device for testing a driver assistance system | |
| CN110775069B (en) | Vehicle driving mode recognition device and method in mixed driving mode | |
| CN113501001A (en) | Driverless vehicle lane change driving control method, driverless vehicle lane change driving control system and driverless vehicle lane change driving terminal | |
| WO2021036083A1 (en) | Driver behavior model development method and device for automatic driving, and storage medium | |
| CN113370996B (en) | Automatic driving lane change following decision method and system and automatic driving vehicle | |
| CN109572689B (en) | Whole vehicle control method and system based on obstacle recognition by radar | |
| EP3570214B1 (en) | Automobile image processing method and apparatus, and readable storage medium | |
| CN112805199A (en) | Self-learning method, device and equipment of automatic driving system and storage medium | |
| RU2678416C2 (en) | Cruise control system of vehicle and method for operation thereof | |
| CN114248805B (en) | Intelligent driving control weight distribution method and system for relieving man-machine conflict | |
| CN111862629A (en) | Method and system for curve overspeed early warning and active speed limiting | |
| CN114954503A (en) | Automatic driving steering fault prediction and redundancy control method and system and electronic equipment | |
| CN113743356A (en) | Data acquisition method and device and electronic equipment | |
| KR20160071164A (en) | Apparatus and Method for Drive Controlling of Vehicle Considering Cut in | |
| CN116279428A (en) | Method and system for automatic parking and obstacle avoidance | |
| CN113415274B (en) | Automatic driving following track planning system, method, vehicle and storage medium | |
| CN115635964A (en) | Vehicle, cruising method and device thereof and electronic equipment | |
| CN114265354A (en) | Vehicle control method and device | |
| CN113581172B (en) | Method for identifying driving scene cut into by intelligent driving vehicle facing target vehicle | |
| CN113232679A (en) | Control method and device for unmanned vehicle | |
| CN117406745A (en) | Method for controlling vehicle, related device and automatic driving vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |